policy
LLM-From-Scratch-To-Advanced-RL-Techniques
ShwaTech · PyTorch
or hover any field below to flag it
Overview
Name
LLM-From-Scratch-To-Advanced-RL-Techniques
Author
ShwaTech
Framework
PyTorch
License
Apache-2.0
Skill type
other
Evidence level
untested
Task description
Build an end-to-end Large Language Model from scratch: implement transformers, train a tiny LLM, modernize with RoPE and RMSNorm, scale training, add Mixture-of-Experts, perform Supervised Fine-Tuning, train a Reward Model, and apply RLHF with PPO and also RLHF with GRPO for alignment and reinforcem
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list LLM-From-Scratch-To-Advanced-RL-Techniques yet.
Datasets that reference this policy
0No datasets reference LLM-From-Scratch-To-Advanced-RL-Techniques yet.